{"id":15188,"date":"2026-01-28T00:00:00","date_gmt":"2026-01-27T23:00:00","guid":{"rendered":"https:\/\/seapop.no\/?p=15188"},"modified":"2026-01-26T12:57:08","modified_gmt":"2026-01-26T11:57:08","slug":"drones-and-artificial-intelligence-bring-new-precision-to-seabird-monitoring","status":"publish","type":"post","link":"https:\/\/seapop.no\/en\/2026\/01\/drones-and-artificial-intelligence-bring-new-precision-to-seabird-monitoring\/","title":{"rendered":"Drones and artificial intelligence bring new precision to seabird monitoring"},"content":{"rendered":"\n<div class=\"wp-block-columns is-layout-flex wp-container-core-columns-is-layout-9d6595d7 wp-block-columns-is-layout-flex\">\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:100%\">\n<h5 class=\"wp-block-heading\" id=\"den-pagaende-nedgangen-i-arktisk-sjois-antas-a-kunne-pavirke-sjofugl-som-hekker-pa-svalbard-men-sammenhengen-er-ikke-bevist-pa-vest-spitsbergen-har-forskere-benyttet-lange-tidsserier-pa-sjoisutbredelse-og-bestandsstorrelse-av-krykkje-rissa-tridactyla-og-polarlomvi-uria-lomvia-for-a-undersoke-om-et-slikt-arsaksforhold-finnes-og-eventuelt-hvilke-mekanismer-som-ligger-bak\">A new study shows how the combination of drone imagery and artificial neural networks can strengthen the monitoring of seabirds along the Norwegian coast. The method delivers high accuracy while minimizing disturbance to birdlife \u2013 an important advance at a time when many seabird species are in decline.<\/h5>\n\n\n\n<p class=\"has-sizing-medium\"><\/p>\n<\/div>\n<\/div>\n\n\n\n<div class=\"wp-block-columns is-layout-flex wp-container-core-columns-is-layout-9d6595d7 wp-block-columns-is-layout-flex\">\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:50%\">\n<h4 class=\"wp-block-heading mt-0\" id=\"sjois-og-sjofuglbestander-i-tilbakegang\"><strong><strong><strong><strong><strong><strong><strong><strong>Image analysis \u2013 the major bottleneck<\/strong><\/strong><\/strong><\/strong><\/strong><\/strong><\/strong><\/strong><\/h4>\n\n\n\n<p class=\"has-sizing-medium\">Traditional seabird surveys have long been time- and resource-intensive, often with a risk of disturbing birds during the breeding season. Drones have made it possible to collect large volumes of image data in a gentler manner, but analysing the resulting vast datasets has remained a challenge. This study addressed this issue by training an advanced detection model based on so-called deep neural networks &#8211; a machine-based and highly simplified imitation of the biological neural tissue of the human brain.<\/p>\n\n\n\n<ul class=\"wp-block-list\"><\/ul>\n\n\n\n<h4 class=\"wp-block-heading\" id=\"effekten-forsinkes-gjennom-naeringskjeden\"><strong><strong><strong><strong><strong><strong><strong><strong><strong>Trained to recognize birds<\/strong><\/strong><\/strong><\/strong><\/strong><\/strong><\/strong><\/strong><\/strong><\/h4>\n\n\n\n<p class=\"has-sizing-medium\">Over three breeding seasons, drone images were collected from 163 colonies along the coast, and more than 23 000 birds were manually annotated. Using an image-processing workflow, the researchers created geometrically corrected, high\u2011resolution aerial image maps (orthomosaics), and adjusted image sizes to ensure compatibility with standard deep\u2011learning frameworks, which are used to train data algorithms. A total of 131 orthomosaics were then used to train the neural network model, which was ultimately evaluated based on its ability to detect and identify bird species in imagery from 32 colonies.<\/p>\n\n\n\n<h4 class=\"wp-block-heading\"><strong><strong><strong><strong><strong><strong><strong><strong><strong>High detection rate<\/strong><\/strong><\/strong><\/strong><\/strong><\/strong><\/strong><\/strong><\/strong><\/h4>\n\n\n\n<p>The fully trained model achieved a detection rate of 87.5 %, meaning it found nearly nine out of ten birds in the image material. Of these detections, 92.4 % of individuals were correctly classified by species. The model also performed well in multi-species colonies, although some errors occurred due to confusion between visually similar species.<\/p>\n\n\n\n<h4 class=\"wp-block-heading\"><strong><strong>Promising methodology<\/strong><\/strong><\/h4>\n\n\n\n<p>The study demonstrated that combining drones and artificial intelligence provides an efficient and scalable solution for monitoring seabird populations. The method reduces the need for manual analysis, saves time and resources, and can improve the basis for informed seabird management. Although new methodologies must be thoroughly calibrated against traditional counting methods, the study shows that this technology has the potential to become an important tool for tracking population trends at a time when many seabird species are under pressure.<\/p>\n\n\n\n<h4 class=\"wp-block-heading\" id=\"les-hele-artikkelen\"><strong>Read the article:<\/strong><\/h4>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/doi.org\/10.1016\/j.ecoinf.2025.103583\" target=\"_blank\" rel=\"noreferrer noopener\"><a href=\"https:\/\/doi.org\/10.1016\/j.ecoinf.2025.103583\" target=\"_blank\" rel=\"noreferrer noopener\">From pictures to numbers: Multi-species seabird surveys using drone imagery and neural networks<\/a><\/a><\/li>\n<\/ul>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:50%\">\n<figure class=\"wp-block-image size-full\"><a href=\"https:\/\/seapop.no\/wp-content\/uploads\/2026\/01\/pxl-20240528-123001133-justert-scaled.jpg\"><img loading=\"lazy\" decoding=\"async\" width=\"2048\" height=\"1634\" src=\"https:\/\/seapop.no\/wp-content\/uploads\/2026\/01\/pxl-20240528-123001133-justert-scaled.jpg\" alt=\"A fieldworker releases a drone from a boat. Photo \u00a9 Sindre Molv\u00e6rsmyr\" class=\"wp-image-15184\" srcset=\"https:\/\/seapop.no\/wp-content\/uploads\/2026\/01\/pxl-20240528-123001133-justert-scaled.jpg 2048w, https:\/\/seapop.no\/wp-content\/uploads\/2026\/01\/pxl-20240528-123001133-justert-300x239.jpg 300w, https:\/\/seapop.no\/wp-content\/uploads\/2026\/01\/pxl-20240528-123001133-justert-1024x817.jpg 1024w, https:\/\/seapop.no\/wp-content\/uploads\/2026\/01\/pxl-20240528-123001133-justert-768x613.jpg 768w, https:\/\/seapop.no\/wp-content\/uploads\/2026\/01\/pxl-20240528-123001133-justert-1536x1226.jpg 1536w\" sizes=\"auto, (max-width: 2048px) 100vw, 2048px\" \/><\/a><figcaption class=\"wp-element-caption\">The researchers behind the study used drones that can be bought off the shelf and released from land or boat, as in this case.<br><em>Photo \u00a9 Sindre Molv\u00e6rsmyr<\/em><\/figcaption><\/figure>\n\n\n\n<figure class=\"wp-block-image size-full\"><a href=\"https:\/\/seapop.no\/wp-content\/uploads\/2026\/01\/artikkel-2-redusert-scaled.png\"><img loading=\"lazy\" decoding=\"async\" width=\"2048\" height=\"1387\" src=\"https:\/\/seapop.no\/wp-content\/uploads\/2026\/01\/artikkel-2-redusert-scaled.png\" alt=\"Orthomosaic of Sm\u00e5v\u00e6rsholman highlighting birds identified by neural network model. Illustration \u00a9 Mie Prik Arnberg.\" class=\"wp-image-15186\" srcset=\"https:\/\/seapop.no\/wp-content\/uploads\/2026\/01\/artikkel-2-redusert-scaled.png 2048w, https:\/\/seapop.no\/wp-content\/uploads\/2026\/01\/artikkel-2-redusert-300x203.png 300w, https:\/\/seapop.no\/wp-content\/uploads\/2026\/01\/artikkel-2-redusert-1024x694.png 1024w, https:\/\/seapop.no\/wp-content\/uploads\/2026\/01\/artikkel-2-redusert-768x520.png 768w, https:\/\/seapop.no\/wp-content\/uploads\/2026\/01\/artikkel-2-redusert-1536x1040.png 1536w\" sizes=\"auto, (max-width: 2048px) 100vw, 2048px\" \/><\/a><figcaption class=\"wp-element-caption\">Orthomosaic of Sm\u00e5v\u00e6rsholman in Flatanger municipality, Tr\u00f8ndelag. Red boxes show what the model identified as seabirds. The inset shows four nesting great black-backed gulls (Larus marinus) and one standing on the ground.<br><em>Illustration \u00a9 Mie Prik Arnberg.<\/em><\/figcaption><\/figure>\n<\/div>\n<\/div>\n\n\n\n<p class=\"has-sizing-medium\">Contact person: <a href=\"https:\/\/seapop.no\/en\/profiles\/sindre-molvaersmyr\/\" data-type=\"page\" data-id=\"14182\">Sindre Molv\u00e6rsmyr<\/a>, Norwegian Institute for Nature Research<\/p>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>A new study shows how the combination of drone imagery and artificial neural networks can &hellip; <\/p>\n<p class=\"read-more-link\"><a href=\"https:\/\/seapop.no\/en\/2026\/01\/drones-and-artificial-intelligence-bring-new-precision-to-seabird-monitoring\/\">Les videre<span class=\"screen-reader-text\"> \u00abDrones and artificial intelligence bring new precision to seabird monitoring\u00bb<\/span><\/a><\/p>\n","protected":false},"author":2,"featured_media":15185,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"_uag_custom_page_level_css":"","footnotes":""},"categories":[1,1],"tags":[427,426,279,428],"class_list":{"0":"post-15188","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-uncategorized","9":"tag-count","10":"tag-deep-learning","11":"tag-modelling","12":"tag-neural-network"},"acf":[],"uagb_featured_image_src":{"full":["https:\/\/seapop.no\/wp-content\/uploads\/2026\/01\/artikkel-redusert-scaled.png",2048,1254,false],"thumbnail":["https:\/\/seapop.no\/wp-content\/uploads\/2026\/01\/artikkel-redusert-150x150.png",150,150,true],"medium":["https:\/\/seapop.no\/wp-content\/uploads\/2026\/01\/artikkel-redusert-300x184.png",300,184,true],"medium_large":["https:\/\/seapop.no\/wp-content\/uploads\/2026\/01\/artikkel-redusert-768x470.png",768,470,true],"large":["https:\/\/seapop.no\/wp-content\/uploads\/2026\/01\/artikkel-redusert-1024x627.png",1024,627,true],"1536x1536":["https:\/\/seapop.no\/wp-content\/uploads\/2026\/01\/artikkel-redusert-1536x941.png",1536,941,true],"2048x2048":["https:\/\/seapop.no\/wp-content\/uploads\/2026\/01\/artikkel-redusert-2048x1254.png",2048,1254,true],"default":["https:\/\/seapop.no\/wp-content\/uploads\/2026\/01\/artikkel-redusert-1200x700.png",1200,700,true],"square":["https:\/\/seapop.no\/wp-content\/uploads\/2026\/01\/artikkel-redusert-400x400.png",400,400,true]},"uagb_author_info":{"display_name":"Erlend Lorentzen","author_link":"https:\/\/seapop.no\/en\/author\/erlend\/"},"uagb_comment_info":0,"uagb_excerpt":"A new study shows how the combination of drone imagery and artificial neural networks can &hellip; Les videre \u00abDrones and artificial intelligence bring new precision to seabird monitoring\u00bb","_links":{"self":[{"href":"https:\/\/seapop.no\/en\/wp-json\/wp\/v2\/posts\/15188","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/seapop.no\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/seapop.no\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/seapop.no\/en\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/seapop.no\/en\/wp-json\/wp\/v2\/comments?post=15188"}],"version-history":[{"count":3,"href":"https:\/\/seapop.no\/en\/wp-json\/wp\/v2\/posts\/15188\/revisions"}],"predecessor-version":[{"id":15194,"href":"https:\/\/seapop.no\/en\/wp-json\/wp\/v2\/posts\/15188\/revisions\/15194"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/seapop.no\/en\/wp-json\/wp\/v2\/media\/15185"}],"wp:attachment":[{"href":"https:\/\/seapop.no\/en\/wp-json\/wp\/v2\/media?parent=15188"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/seapop.no\/en\/wp-json\/wp\/v2\/categories?post=15188"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/seapop.no\/en\/wp-json\/wp\/v2\/tags?post=15188"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}